Skip to main content
Log in

Abstract

Pixel processing is the most fundamental performance bottleneck in high-end three-dimensional graphics systems. This paper presents the design of a specialized custom VLSI graphics chip that was implemented with one million transistors and is capable of processing pixels at extremely rapid rates close to one nanosecond. This was made possible by utilizing a large number of identical pipelined pixel processors that operate in a purely systolic fashion. The chip has been designed at the IBM Research Division's Thomas J. Watson Research Center.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. H. Fuchs and J. Poulton, “Pixel Planes: A VLSI-Oriented Design for a Raster Graphics Engine,”VLSI Design, 2(3): 3rd. Quarter, 1981, pp 20–28.

    Google Scholar 

  2. Bart Locanthi, “Object Oriented Raster Displays,”Proceedings of Caltech Conference on VLSI, January 1979, pp. 215–225.

  3. Daniel S. Whelan, “A Rectangular Area Filling Display System Architecture,”Computer Graphics, 16(3): July 1982, pp. 147–153.

    Article  Google Scholar 

  4. S. Demetrescu, “High Speed Image Rasterization Using Scan Line Access Memories,”Proc. 1985 Chapel Hill Conference on VLSI, Computer Science Press, 1985, pp 221–243.

  5. J.H. Jackson, “Dynamic Scan-converted images with a Frame Buffer Display Device,”Computer Graphics, 14(3): July 1980, pp. 163–169.

    Article  Google Scholar 

  6. H. Niimi, Y. Imai, M. Murakami, S. Tomita, and H. Hagiwara, “A Parallel Processor System for Three Dimensional Color Graphics,”Computer Graphics, 18(3): July 1984, pp. 67–76.

    Article  Google Scholar 

  7. N. Gharachorloo and C. Pottle, “SUPER BUFFER: A Systolic VLSI Graphics Engine for Real Time Raster Image Generation,”Proc. 1985 Chapel Hill Conference on VLSI, Computer Science Press, 1985, pp. 285–305.

  8. A.J. Myers,An Efficient Visible Surface Program, Ohio State University, Report to the NSF, July 1975.

  9. G.S. Watkins,A Real Time Visible Surface Algorithm, University of Utah, Computer Science Department, June 1970.

  10. N.F. Goncalves,IORA: A Racefree CMOS Technique for Register Transfer Systems, Ph.D. Thesis. Katholieke Univeriteit Leuven, Belgium. 1985.

    Google Scholar 

  11. N. Gharachorloo,Super Buffer: A Systolic VLSI Graphics Engine for Real Time Raster Image Generation, Ph.D. Thesis, Electrical Engineering Department, Cornell Univ., Ithaca, NY. August 1985.

    Google Scholar 

  12. T. Nishizawa, T. Ohgi, K. Nagatomi, H. Kamiyama, K. Maenobu, and M. Fujiwara, “A Hidden Surface Processor for 3-Dimension Graphics,”ISSCC, Feb. 1988, pp. 166–167.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Gharachorloo, N., Gupta, S., Hokenek, E. et al. A million transistor systolic array graphics engine. J VLSI Sign Process Syst Sign Image Video Technol 1, 35–43 (1989). https://doi.org/10.1007/BF00932064

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00932064

Keywords

Navigation